Instructions to use bjivanovich/swift-1.5-27b-coding-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use bjivanovich/swift-1.5-27b-coding-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bjivanovich/swift-1.5-27b-coding-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bjivanovich/swift-1.5-27b-coding-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bjivanovich/swift-1.5-27b-coding-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Ollama
How to use bjivanovich/swift-1.5-27b-coding-GGUF with Ollama:
```
ollama run hf.co/bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bjivanovich/swift-1.5-27b-coding-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bjivanovich/swift-1.5-27b-coding-GGUF with Docker Model Runner:
```
docker model run hf.co/bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M
```

Lemonade

How to use bjivanovich/swift-1.5-27b-coding-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.swift-1.5-27b-coding-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bjivanovich/swift-1.5-27b-coding-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bjivanovich/swift-1.5-27b-coding-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "bjivanovich/swift-1.5-27b-coding-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

swift-1.5-27b-coding-GGUF

Official GGUF quantized weights for swift-1.5-27b-coding, a specialized 27B parameter coding model fine-tuned using DoRA on bjivanovich/code-py-rust-cpp-50k (covering Python, Rust, C++, and multi-step reasoning).

All quantizations were generated using an importance matrix (imatrix) calibrated directly on domain-specific programming samples.

Quantization Details

File Name	Quant Method	Approx Size	Recommended Use Case
`swift-1.5-27b-coding-Q4_K_M.gguf`	Q4_K_M (imatrix)	16.8 GB	Optimal balance of speed, size, and reasoning quality (fits in 24GB GPUs).
`swift-1.5-27b-coding-Q5_K_M.gguf`	Q5_K_M (imatrix)	19.5 GB	High fidelity; preserves subtle syntax nuances.
`swift-1.5-27b-coding-Q6_K.gguf`	Q6_K (imatrix)	22.4 GB	Near-lossless precision.
`swift-1.5-27b-coding-Q8_0.gguf`	Q8_0	29.0 GB	Reference standard precision.
`mmproj-BF16.gguf`	BF16	0.9 GB	Vision projector, needed only for image and video input.
`swift-27b-coding.imatrix`	Importance Matrix	13.6 MB	Calibration data used for quantized layers.

Training & Specialization

Base Architecture: 27B Parameters
Technique: DoRA (Weight-Decomposed Low-Rank Adaptation)
Dataset: bjivanovich/code-py-rust-cpp-50k (50,000 samples)
- Python: 59.0%
- C++: 20.4%
- Rust: 15.5%
- Reasoning: 5.0%

Prompt Template (ChatML)

<|im_start|>user
Write a thread-safe generic queue in Rust using Arc and Mutex with unit tests.<|im_end|>
<|im_start|>assistant

Downloads last month: 382

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for bjivanovich/swift-1.5-27b-coding-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

ukisai/Swift-1.5-Qwen3.8-27b

Finetuned

ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-MTP

Quantized

(12)

this model